# Gemini 3.6 Flash vs MiniMax-M3

> Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 43.5 on the Noometry Index. MiniMax-M3 costs 2.9× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-6-flash-vs-minimax-m3
- Last updated: 2026-10-10
- Shared benchmarks: 34

## Summary

- They share 34 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 9 categories and MiniMax-M3 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.9 to 29.3.
- The biggest single-benchmark swing is Chess Puzzles: 43% for Gemini 3.6 Flash and 14% for MiniMax-M3.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.6 Flash.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 1M.
- MiniMax-M3 has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.6 Flash | MiniMax-M3 |
|---|---|---|
| Provider | Google | MiniMax |
| Noometry Index | 54.1 | 43.5 |
| Rank | 30 | 81 |
| Context | 1.05M | 1M |
| Input $/M | $0.75 | $0.30 |
| Output $/M | $3.75 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.6 Flash: 49.6 (#45)
- MiniMax-M3: 41.5 (#111)

| Benchmark | Gemini 3.6 Flash | MiniMax-M3 |
|---|---|---|
| FrontierCode | 34.4% | 14.7% |
| LMArena WebDev | 1536 | 1482 |
| SciCode | 52.7% | 47.1% |
| LMArena Coding | 1492 | 1470 |
| ALE-Bench | 715.52 | 640.02 |
| DeepSWE | 46.7% | — |
| WeirdML | 56.1% | — |

## Agentic & Tool Use

- Gemini 3.6 Flash: 32.4 (#56)
- MiniMax-M3: 22.5 (#121)

| Benchmark | Gemini 3.6 Flash | MiniMax-M3 |
|---|---|---|
| APEX-Agents | 46.9% | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| GDP.pdf | 14% | — |
| Vending-Bench 2 | — | 2,158 |

## Reasoning

- Gemini 3.6 Flash: 58.9 (#20)
- MiniMax-M3: 29.3 (#83)

| Benchmark | Gemini 3.6 Flash | MiniMax-M3 |
|---|---|---|
| NYT Connections (extended) | 89% | 65.1% |
| CritPt | 10.6% | 3.7% |
| Chess Puzzles | 43% | 14% |
| LMArena Hard Prompts | 1486 | 1447 |
| Mystery Game Puzzles | 30% | 8% |
| DTBench | 95.5% | 78.9% |
| LMCA | 44.9% | 33.7% |
| Epoch Capabilities Index | 154.36 | 147 |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | — | 45.8% |
| ARC-AGI-1 | 91.2% | — |
| Surface Evolver Bench | — | 55% |
| ForecastBench | — | 61.4 |

## Math

- Gemini 3.6 Flash: 57.0 (#33)
- MiniMax-M3: 39.1 (#83)

| Benchmark | Gemini 3.6 Flash | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.2% | 71.1% |
| ProofBench | 36% | 18% |
| LMArena Math | 1504 | 1432 |
| FrontierMath (Tiers 1-3) | 58.9% | — |
| FrontierMath Tier 4 | 22% | — |
| MathArena Final-Answer Competitions | 70.8% | — |

## Knowledge

- Gemini 3.6 Flash: 67.8 (#7)
- MiniMax-M3: 58.4 (#32)

| Benchmark | Gemini 3.6 Flash | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 94.1% | 90.9% |
| LMArena Expert | 1489 | 1462 |
| SimpleQA Verified | 66.2% | — |

## Multimodal

- Gemini 3.6 Flash: 38.7 (#55)
- MiniMax-M3: 39.5 (#45)

| Benchmark | Gemini 3.6 Flash | MiniMax-M3 |
|---|---|---|
| LMArena Vision | 1297 | 1254 |
| LMArena Document | 1456 | 1435 |
| Blueprint-Bench 2 | 31.2% | — |
| Furniture Assembly | 23.3% | — |

## Multilingual

- Gemini 3.6 Flash: 56.8 (#17)
- MiniMax-M3: 53.2 (#70)

| Benchmark | Gemini 3.6 Flash | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1470 | 1420 |
| LMArena Chinese | 1530 | 1465 |
| LMArena French | 1501 | 1445 |
| LMArena German | 1478 | 1424 |
| LMArena Japanese | 1477 | 1381 |
| LMArena Korean | 1435 | 1372 |
| LMArena Russian | 1490 | 1430 |
| LMArena Spanish | 1477 | 1431 |

## Instruction Following

- Gemini 3.6 Flash: 77.2 (#27)
- MiniMax-M3: 75.7 (#56)

| Benchmark | Gemini 3.6 Flash | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1467 | 1433 |

## Long Context

- Gemini 3.6 Flash: 45.1 (#47)
- MiniMax-M3: 44.2 (#68)

| Benchmark | Gemini 3.6 Flash | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1475 | 1445 |

## Writing & Preference

- Gemini 3.6 Flash: 68.3 (#26)
- MiniMax-M3: 62.3 (#79)

| Benchmark | Gemini 3.6 Flash | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1478 | 1433 |
| LMArena Creative Writing | 1464 | 1405 |
| LMArena Multi-Turn | 1481 | 1441 |
| EQ-Bench Creative Writing | 1604 | — |
| EQ-Bench 4 | — | 1150 |

## FAQ

### Is Gemini 3.6 Flash better than MiniMax-M3?

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 43.5 on the Noometry Index. MiniMax-M3 costs 2.9× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.6 Flash or MiniMax-M3?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Gemini 3.6 Flash lists at $0.75 and $3.75.

### Is Gemini 3.6 Flash or MiniMax-M3 better for coding?

Gemini 3.6 Flash scores higher on coding benchmarks: 49.6 versus 41.5 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.6 Flash does, with 1.05M tokens against 1M.

### How many benchmarks do Gemini 3.6 Flash and MiniMax-M3 share?

34 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and MiniMax-M3 has 41.